Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3165 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.3257. Min Act: -0.0000

Data Index: 92595 (C4 (Web Text))

Max Activating Token Index: 338

Text #1

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2499. Min Act: -0.0000

Data Index: 1042430 (C4 (Web Text))

Max Activating Token Index: 223

Text #2

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2508. Min Act: -0.0000

Data Index: 995989 (C4 (Web Text))

Max Activating Token Index: 408

Text #3

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2376. Min Act: -0.0000

Data Index: 895217 (C4 (Web Text))

Max Activating Token Index: 486

Text #4

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2401. Min Act: -0.0000

Data Index: 867393 (C4 (Web Text))

Max Activating Token Index: 290

Text #5

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2785. Min Act: -0.0000

Data Index: 359152 (C4 (Web Text))

Max Activating Token Index: 189

Text #6

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2492. Min Act: -0.0000

Data Index: 1186292 (C4 (Web Text))

Max Activating Token Index: 240

Text #7

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2506. Min Act: -0.0000

Data Index: 200721 (C4 (Web Text))

Max Activating Token Index: 230

Text #8

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2345. Min Act: -0.0000

Data Index: 563621 (C4 (Web Text))

Max Activating Token Index: 219

Text #9

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2370. Min Act: -0.0000

Data Index: 278447 (C4 (Web Text))

Max Activating Token Index: 125

Text #10

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2466. Min Act: -0.0000

Data Index: 241865 (C4 (Web Text))

Max Activating Token Index: 952

Text #11

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2269. Min Act: -0.0000

Data Index: 430290 (C4 (Web Text))

Max Activating Token Index: 99

Text #12

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2095. Min Act: -0.0000

Data Index: 1336825 (C4 (Web Text))

Max Activating Token Index: 622

Text #13

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2097. Min Act: -0.0000

Data Index: 1245130 (C4 (Web Text))

Max Activating Token Index: 1017

Text #14

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2286. Min Act: -0.0000

Data Index: 542001 (C4 (Web Text))

Max Activating Token Index: 678

Text #15

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2213. Min Act: -0.0000

Data Index: 892039 (C4 (Web Text))

Max Activating Token Index: 362

Text #16

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.1981. Min Act: -0.0000

Data Index: 488364 (C4 (Web Text))

Max Activating Token Index: 215

Text #17

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2159. Min Act: -0.0000

Data Index: 218725 (C4 (Web Text))

Max Activating Token Index: 87

Text #18

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.1918. Min Act: -0.0000

Data Index: 11728 (C4 (Web Text))

Max Activating Token Index: 660

Text #19

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2140. Min Act: -0.0000

Data Index: 414354 (C4 (Web Text))

Max Activating Token Index: 560